# Search Across Metadata
## Why Search Matters
Locating the right data asset in large enterprises often feels like searching for a needle in a haystack. Business users may not be familiar with schema names or column structures, while analysts spend a significant amount of time manually mapping objects. Traditional search tools rely on exact keywords and return long, unrefined lists that require further interpretation.
**askEdgi** simplifies this process by interpreting natural language queries and returning context-aware results. Instead of focusing only on technical matches, it understands business intent and retrieves relevant metadata across the platform.
### What Can Be Searched
askEdgi supports natural language search across multiple metadata domains, including:
* **Data Catalog:** Tables, columns, schemas, and files
* **Business Glossary**: Terms, categories, and subcategories
* **Projects**: Ongoing Projects in the organisation
* **Service Desk Template:** Active service desk templates
**Please refer to the following Document on what can be searched using Edgi**
* [Discovery and Analytics Mode](https://docs.ovaledge.com/ai/askedgi-prompts#discovery-and-analytics-mode)
### Predefined Prompt Library
The workspace features a predefined set of AI prompts for quick interaction and discovery.
**Examples**
* What can you do?
* Where is my sales data?
* Find a dataset that helps me calculate the highest average air temperature in the US?
Selecting any predefined prompt instantly triggers the AI assistant to perform the corresponding operation.
{% hint style="info" %}
Using simple, specific language in prompts helps generate more accurate and helpful responses. All conversations maintain their context until the thread is closed.
{% endhint %}
## **Use Case & Real-Life Scenario**
A newly onboarded marketing analyst is assigned the task of analyzing customer sentiment. Without prior knowledge of schemas or storage structures, the analyst enters the query:\
“Which tables contain customer feedback?”
**askEdgi immediately returns results such as:**
* customer\_reviews
* product\_feedback
* support\_comments
**Each result provides:**
* Object name and description
* Stewardship details
* Tags and associated terms
* Row count
* Data quality and curation scores
* Direct link to the summary page
* Option to add the object to the Workspace
The analyst continues with the query:
“**What is the data quality score of the table customer\_reviews?**”
The askEdgi delivers data quality and curation scores, along with ownership and stewardship information. Within two queries, the analyst identifies the correct table, understands its context, and verifies compliance classifications - without writing SQL or browsing schemas.
**Example Searches**
* **Search Across Glossary**: Returns business terms, categories, and definitions.
* **Search Across Catalog**: Retrieves technical metadata, including tables, schemas, and columns.
### Availability
* **Public** – Available (metadata search across catalog, glossary, tags, stories, and question wall).
* **SaaS** – Available (full metadata coverage).
* **On-Prem** – Limited to catalog search only (workspace analysis and enrichment unavailable).
## **Session Context and Security**
All workspace activities operate within a secure environment. Uploaded files, catalog integrations, and conversational interactions remain confined to the authenticated session.
Data is not transmitted externally or stored permanently beyond configured retention periods.
***
Copyright © 2025, OvalEdge LLC, Peachtree Corners, GA USA
---
# Agent Instructions: Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://docs.ovaledge.com/ai/askedgi/search-across-metadata.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.